{"id":"W4388828744","doi":"10.2196/46087","title":"A Novel Approach for the Early Detection of Medical Resource Demand Surges During Health Care Emergencies: Infodemiology Study of Tweets","year":2023,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; University of Toronto; Artificial Intelligence in Medicine (Canada); York University","funders":"Natural Sciences and Engineering Research Council of Canada; International Development Research Centre","keywords":"Sentiment analysis; Granger causality; Resource (disambiguation); Social media; Pandemic; Coronavirus disease 2019 (COVID-19); Health care; Business; Causality (physics); Medical emergency; Computer science; Medicine; Economics; Econometrics; Artificial intelligence; Economic growth; World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009633921,0.0005230682,0.0003507317,0.00454293,0.0005530305,0.001722264,0.0003384634,0.0006173248,0.001770061],"category_scores_gemma":[0.004320219,0.0001466571,0.0005382639,0.002539199,0.0003432779,0.001794681,0.0007320818,0.0006373998,0.0009006165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000642092,"about_ca_system_score_gemma":0.0005971145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003502491,"about_ca_topic_score_gemma":0.004365125,"domain_scores_codex":[0.9995172,0.0001171559,0.0000512453,0.0001318633,0.0001136728,0.00006891674],"domain_scores_gemma":[0.9971976,0.001434639,0.0005786679,0.0001260994,0.0005116232,0.0001513138],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00134118,0.0008814236,0.5204194,0.001188332,0.0003814143,0.001986201,0.007033226,0.006868375,0.04252696,0.01377427,0.02579981,0.3777995],"study_design_scores_gemma":[0.00006157711,0.0006446088,0.6122385,0.0003688427,0.0003138714,0.00130296,0.02154682,0.2900034,0.01391329,0.01202706,0.0474292,0.0001497022],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8825726,0.002147277,0.06846666,0.003954814,0.0009481863,0.001081631,0.01592495,0.0006089575,0.02429502],"genre_scores_gemma":[0.9644975,0.0005215943,0.02830444,0.0002492861,0.0003833568,0.0003472964,0.002931343,0.00003618051,0.002728992],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00454293,"threshold_uncertainty_score":0.006964207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1045707389461139,"score_gpt":0.4504025157345979,"score_spread":0.345831776788484,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}